Instructions to use LGxNDs/Geeked-Out-Quantization-Software with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LGxNDs/Geeked-Out-Quantization-Software with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="LGxNDs/Geeked-Out-Quantization-Software",
	filename="Qwen3.6-GeekedOutAi-35B-A3B-BF16-IQ2_M-00001-of-00002.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use LGxNDs/Geeked-Out-Quantization-Software with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf LGxNDs/Geeked-Out-Quantization-Software:IQ2_M
# Run inference directly in the terminal:
llama-cli -hf LGxNDs/Geeked-Out-Quantization-Software:IQ2_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf LGxNDs/Geeked-Out-Quantization-Software:IQ2_M
# Run inference directly in the terminal:
llama-cli -hf LGxNDs/Geeked-Out-Quantization-Software:IQ2_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf LGxNDs/Geeked-Out-Quantization-Software:IQ2_M
# Run inference directly in the terminal:
./llama-cli -hf LGxNDs/Geeked-Out-Quantization-Software:IQ2_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf LGxNDs/Geeked-Out-Quantization-Software:IQ2_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf LGxNDs/Geeked-Out-Quantization-Software:IQ2_M

Use Docker

docker model run hf.co/LGxNDs/Geeked-Out-Quantization-Software:IQ2_M

LM Studio
Jan
Ollama
How to use LGxNDs/Geeked-Out-Quantization-Software with Ollama:
```
ollama run hf.co/LGxNDs/Geeked-Out-Quantization-Software:IQ2_M
```

Unsloth Studio new

How to use LGxNDs/Geeked-Out-Quantization-Software with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for LGxNDs/Geeked-Out-Quantization-Software to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for LGxNDs/Geeked-Out-Quantization-Software to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for LGxNDs/Geeked-Out-Quantization-Software to start chatting

Pi new

How to use LGxNDs/Geeked-Out-Quantization-Software with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf LGxNDs/Geeked-Out-Quantization-Software:IQ2_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "LGxNDs/Geeked-Out-Quantization-Software:IQ2_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use LGxNDs/Geeked-Out-Quantization-Software with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf LGxNDs/Geeked-Out-Quantization-Software:IQ2_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default LGxNDs/Geeked-Out-Quantization-Software:IQ2_M

Run Hermes

hermes

Docker Model Runner
How to use LGxNDs/Geeked-Out-Quantization-Software with Docker Model Runner:
```
docker model run hf.co/LGxNDs/Geeked-Out-Quantization-Software:IQ2_M
```

Lemonade

How to use LGxNDs/Geeked-Out-Quantization-Software with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull LGxNDs/Geeked-Out-Quantization-Software:IQ2_M

Run and chat with the model

lemonade run user.Geeked-Out-Quantization-Software-IQ2_M

List all available models

lemonade list

LGxNDs commited on 22 days ago

Commit

6b42c79

verified ·

1 Parent(s): 55d6ba1

Upload 2 files

Browse files

This repository contains a Qwen3.6 model quantized using IQ2_M 2-bit quantization via the GGUF format. The IQ2_M scheme is part of the Intelligent Quants (IQ) family, designed to deliver extreme low-bit precision while preserving model quality through mixed-precision techniques.

**Model Overview:**
Qwen3.6 represents a series of large language models featuring advanced architecture optimizations including grouped query attention (GQA), sliding window attention, and high-quality tokenization for efficient training and inference. These models are designed to deliver strong reasoning capabilities across diverse tasks while maintaining computational efficiency through architectural innovations like multi-token prediction and MoE-style routing.

**IQ2_M Quantization Process:**
IQ2_M is a 2-bit quantization scheme that combines multiple sub-precision levels (2 bits per weight) using intelligent bit allocation strategies. It employs mixed-precision where different weights receive varying bit allocations based on their sensitivity, with critical parameters preserved in higher precision while less important weights are packed into minimal bit formats. The "M" variant specifically balances quality retention with memory efficiency through optimized scaling factors and block-wise quantization, achieving significant model size reduction while maintaining usable performance for practical applications.

Files changed (3) hide show

.gitattributes +2 -0
Qwen3.6-GeekedOutAi-35B-A3B-BF16-IQ2_M-00001-of-00002.gguf +3 -0
Qwen3.6-GeekedOutAi-35B-A3B-BF16-IQ2_M-00002-of-00002.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Qwen3.6-GeekedOutAi-35B-A3B-BF16-IQ2_M-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3.6-GeekedOutAi-35B-A3B-BF16-IQ2_M-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text

Qwen3.6-GeekedOutAi-35B-A3B-BF16-IQ2_M-00001-of-00002.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c0681e394d4ad4e815297b2388307134573c1a3dd2a099e0b96b48336b4fcec9
+size 8302924576

Qwen3.6-GeekedOutAi-35B-A3B-BF16-IQ2_M-00002-of-00002.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:3b9ac80f9a243730299dc337795df3571b206caf8ca8ce3b49b1e6000a092345
+size 3356312000